© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 3444
    Prev
    Next
    INDEX
    Explanations

    phrases related to military operations and political events

    oai_token-act-pair · gpt-3.5-turbo

    references to specific nationalities or groups involved in geopolitical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     selfies
    -0.63
     selfie
    -0.63
     havoc
    -0.61
     thriller
    -0.59
     thrill
    -0.59
     Pepe
    -0.59
    anchester
    -0.58
     brisk
    -0.57
    latable
    -0.57
     sandwiches
    -0.57
    POSITIVE LOGITS
     authorities
    1.40
     superiors
    1.29
     administrators
    1.23
     manag
    1.16
     supervisors
    1.14
     officials
    1.13
     administrations
    1.13
     regulators
    1.10
     administration
    1.08
     commissioners
    1.08
    Activations Density 0.597%

    No Known Activations